KI-Tools Changelog Hub

v0.3.290

6. Oktober 2026

• •Added an optional offset field to the WebFetch tool input for reading on through long pages
• •Fixed failed Claude in Chrome tool calls dropping the result's _meta: when the result has one, tool_use_result is now { content, _meta }, as for other MCP tools
• •Fixed deny and ask rules missing toolAliases tools when written with a wildcard (Bash*), a match-all pattern (Bash(**), also on the mapped name), or an input field also in disallowedTools
• •Fixed a user message sent again under the same uuid being replayed (--replay-user-messages) while the first copy still waited for its turn; its replay now comes when a turn takes it
• •Fixed includePartialMessages streams leaving a message without message_stop when the stream was cut, interrupted or fell back to non-streaming
• •Changed user_message_uuid, user_message_uuids and resume_reason to also be set on a turn a restarted worker resumes from a permission answer or from tool calls still in flight
• •Updated to parity with Claude Code v2.1.290

v1.0.4

6. Oktober 2026

• •Tool patterns and `--no-mcp`: --tools and --exclude-tools accept * patterns, for example --tools read,codemode,'mcp__radius__*' keeps only one MCP server's tools. --tools now keeps MCP tools unless an entry starts with mcp__, and --no-mcp turns off MCP for one run. See Tools and MCP tools.
• •Codemode persists images: tools.read() on an image file now gives back an image block that image() can show. See Call tools.
• •Added * patterns to --tools and --exclude-tools, for example --tools read,codemode,'mcp__radius__*'
• •Added --no-mcp to disable the built-in MCP support for one run
• •Fixed syntax highlighting losing colors after the first line of multiline strings and comments in fenced code blocks (#10143)
• •Fixed codemode scripts not receiving images from read: tools.read() now resolves to an image block for image files, which image() shows (#10251)
• •Fixed MCP OAuth sign-in failing with invalid_redirect_uri on servers with OpenID Connect client registration, such as mcp.modem.dev: pi now registers as a native client (#10493)
• •Fixed --tools removing MCP tools, which left pi --tools codemode without any MCP servers. --tools now keeps MCP tools unless an entry starts with mcp__
• •Fixed MCP session shutdown returning while a server was still connecting, leaving its transport open until the server answered or timed out (#10249)
• •Fixed system prompt rules and the skills hint naming tools hidden by prepareLoadout. Hidden tools are left out of the rules, the skills hint names no tool when the file reader is hidden, and codemode shows each tool's prompt guidelines with its declaration; ToolLoadout gains getPromptGuidelines() (#10343)
• •Fixed Bedrock requests that fail with The pending stream has been canceled after a stalled HTTP/2 connection not being retried automatically (#10379)
• •Fixed codemode scripts that patch built-ins (for example Array.prototype.toJSON = ...) crashing pi and leaving the tool call unsettled. Built-ins are now frozen before the script runs, so such patches have no effect (#10444)

OpenClaw2026.10.1-beta.1Neu

openclaw 2026.10.1-beta.1

5. Oktober 2026

• •Sessions and memory: preserved usage across registry changes, delivered worker attachments from remote workspaces, prevented queued cancellations and transcript aliases from stalling active turns, kept continuation signatures aligned, and migrated embedding caches in bounded batches with oversized-row reporting. (#164217, #164219, #163708, #164230, #164251, #164289, #164287, #164303) Thanks @vincentkoc.
• •Replies and media: restored inline playback for local videos, replaced rejected media links with useful errors, kept Telegram progress updates free of preview cards, and fixed speech-only replies when reasoning is enabled. (#164137, #163727, #164285, #164256) Thanks @ivan-magda, @obviyus, and @Twilight-Networks.
• •Updates and Doctor: improved serving-verdict recovery guidance, kept repairs working with read-only managed config, removed repeated config, backup, metadata, and pnpm-root probes, reported successful cleanup as progress without corrupting JSON output, and treated a still-starting Gateway as a warning. (#164193, #161924, #164235, #162259, #164182, #164186, #164183, #164184, #163477, #164261, #162236, #164312) Thanks @DonnieFi, @JD8855122, @Patrick-Erichsen, and @waynegault.
• •Windows workspaces and browser startup: fixed empty and nested Windows worktree creation, improved Linux Chromium discovery, and automatically started Playwright Chromium on ARM64. (#164202, #164249, #163510, #163281) Thanks @ly85206559, @jesse-merhi, and @obviyus.
• •Cloud workers and Crabbox: surfaced the real cloud-worker failure, enforced Linux leases, overlapped worker-bundle downloads with bootstrap, removed unrelated warm-image cleanup waits, and prevented slow reads or unsupported backends from stranding workers. (#164129, #164187, #164128, #164231)
• •Plugins, Codex, and MCP: preserved Bun package-import capture, reduced prerelease metadata requests, kept expired remote-exec approvals from poisoning auth profiles, restored node policy hooks, synchronized MCP forms/files/context, and routed background skill reviews through Workshop proposals. (#164223, #164185, #164237, #164270, #164277, #164292)
• •Added inactive-foundation support for incognito actor memory and Codex history routing. (#164224)
• •Migrated existing agents to local Claws. (#162329) Thanks @Patrick-Erichsen.
• •Reduced Sessions-board and state-path overhead by serving prepared facts, reusing card payloads per store revision, moving lifecycle mutations off the main thread, and retaining canonical state handles. (#164218, #164301, #163815, #164110)
• •Preserved plugin lifecycle fences for cancelled queued turns and retained investigated failures in ready PR reviews. (#164247, #164253) Thanks @vincentkoc.
• •Honored agent-local model aliases in status summaries. (#164126, #164115) Thanks @ooiuuii and @obviyus.
• •Kept Gateway tests on the selected Bun runtime and ran native Codex subagent checks in Docker. (#164276, #164163)
• •Left webhook config migrations to Doctor and avoided Nextcloud Talk webhook migration for unconfigured channels.
• •channel-webhook-listener-config-inputs began warning on 2026-09-26; migrate to legacyWebhook for canonical listener config. See /gateway/doctor/config-migrations#channel-webhook-listeners.
• •session-manager-sync-persistence began warning on 2026-10-01; await the matching Async-suffixed SessionManager method and its rewrite commit. See /plugins/sdk-migration/how-to-migrate#await-session-transcript-persistence.

Codex CLIv0.160.1Neu

0.160.1

5. Oktober 2026

• •Preserve SYSTEMROOT, TEMP, and TMP when launching remote stdio MCP servers with explicitly configured remote environment variables, allowing Unix hosts to retain the Windows executor's startup environment.
• •#51121: Backport Windows remote MCP environment preservation to 0.160.

Claude Codev2.1.290Neu

Claude Code 2.1.290

5. Oktober 2026

• •Added serverToolUses to the result of a mod's turn.step hook: the tool calls the API ran itself (the advisor), each with its id, name, input, start and end
• •Added agentId to the tool.check event of plugin hooks, so a hook can tell a subagent's permission check from the main session's
• •Added ceiling to the question and verdict a mod's tool.check hook reads, naming the approval an organization requires for a tool
• •Added ThemeKey and Color types to the plugin hooks typings, so an editor lists the theme colors a mod's drawing can name
• •Added to claude plugin validate: each hook a mod registers at a gating site is listed with whether it has a .catch (gatingHooks under --json)
• •Added a Deny button to the Claude apps gateway's sign-in approval page: it ends the pending sign-in, so the waiting terminal stops within seconds
• •Added claude attach <name> and claude logs <name>: part of a session name works in place of the id
• •Added /claude-api managed-agents-onboard <url> to set up the Managed Agents pattern a page describes as ant apply files
• •Added /claude-api managed-agents-onboard <quickstart-name> to build a Console quickstart template, such as deep-researcher, with the ant CLI
• •Added a warning when a managed settings file is a link to a file outside the managed settings folder
• •Added a /status and doctor warning when managed settings ignore user-configured sandbox allowRead paths or allowed domains
• •Fixed requests failing behind proxies and gateways that reject one of Claude Code's beta headers with a status other than 400, or together with a second beta
• •Fixed long sessions with hundreds of images getting stuck on "Request rejected as unprocessable by the model" errors
• •Fixed a turn ending at once when the API's output content filter stopped a reply while Claude was still thinking; the request is now retried once before the error is shown
• •Fixed resumed subagents and teammates losing their earlier thinking and prompt cache after receiving a message mid-run
• •Fixed WebFetch silently dropping page text past 100,000 characters; it now says how much was unread and takes an offset to read on
• •Fixed a crash ("Maximum call stack size exceeded") when a response nested lists or quotes thousands of levels deep
• •Fixed /rewind not listing a prompt sent while Claude was still working
• •Fixed scheduled tasks (/loop with an interval, reminders) silently not coming back on resume once the conversation was compacted; covers compactions made from this version on
• •Fixed scheduled tasks set in the foreground never firing after a ← or /background hand-off, and recurring ones firing an extra run on every resume, respawn or fork
• •Fixed headless --json-schema runs exiting non-zero with is_error: true on a success result when the connection dropped after the structured output was already delivered
• •Fixed plan mode letting the auto mode classifier approve non-read-only connector tools that carry a server-pushed ask policy
• •Fixed a project CLAUDE.md, rule or AGENTS.md symlinked outside the working directories loading under permissions.blockReadsOutsideWorkingDirectories or a Read deny rule
• •Fixed URL allow and deny patterns with a wildcard inside an xn-- host label matching differently from one process to the next
• •Fixed an MCP server provided by your organization being relisted as your own after signing in or reconnecting, including from a late result in headless and SDK sessions
• •Fixed /ultrareview dropping uncommitted changes without a warning on Windows when git stash create failed, and refusing them after a git add -N file was deleted or moved
• •Fixed the plansDirectory setting's project-root check for paths that contain a backslash on macOS and Linux
• •Fixed replies in very long Remote Control and cloud sessions that could appear a block at a time instead of streaming in
• •Fixed the background daemon's log passing terminal control characters to the screen under claude daemon run and claude daemon logs; they now show as \uXXXX escapes
• •Self-hosted runner: Fixed a crafted, very long line of a session's error output freezing the runner for several seconds
• •Fixed a plugin hook with a .catch being unloaded, and its .catch skipped, when the hook kept the hooks worker busy on a prompt or tool call
• •Fixed a mod's turn.step result listing a tool call that a mid-response model fallback had discarded
• •Fixed a Cowork cloud session's reply sometimes never finishing when its container restarted just after Claude sent a message or a file
• •Fixed claude plugin validate and plugin loading refusing a hooks module that destructures an option named like one of its top-level functions
• •Fixed /ultrareview failing to upload uncommitted changes when core.safecrlf=true is set in git's configuration
• •Fixed the effort level changing when a flagged message is retried on a fallback model that has a different level saved in settings
• •Windows: Fixed multi-line ! shell blocks in skills and commands failing when the file is saved with CRLF line endings
• •Fixed Claude Code hanging until killed when a /permissions tab was clicked while searching in fullscreen mode
• •Fixed conversation compaction sometimes failing with a "null is not an object" error
• •Fixed plugin hooks reading an empty answer on turn.complete for a subagent that hands its report back in auto mode
• •Fixed a mod being unloaded without a message when a refresh followed its failed reload; its failure line now says the version loaded before is unloaded
• •Fixed a mod's prompt.submit hook that drops a prompt after calling next(e) being ignored silently: the hook is now reported as failed, by name
• •Fixed a mod's pane or band being redrawn without end when it followed its end over a tree that changed height at every drawing
• •Fixed an image read on macOS and Windows being able to return a file outside what was approved, through a link swapped in mid-read
• •Fixed a case where a user-installed mod could get an organization's plugin unloaded; the mod is now the one unloaded
• •Fixed disableClaudeAiConnectors and allowedMcpServers URL rules not being applied to some MCP entries declared in .mcp.json, plugins or agents
• •Fixed a mod's inline pane being redrawn without end when its tree changed height at every drawing
• •Fixed an @-mention under the read block or --restricted being able to read a file outside the working directories through a link changed mid-read
• •Fixed Esc in the agents view confirming "Press enter again to restart this session — it isn't responding"; Esc now just reopens the session
• •Fixed agent view losing a background session's /loop run count, countdown and live status line after the session enters a worktree that it creates
• •Fixed claude agents sessions in manual permission mode asking for approval to read an image pasted into a reply or a new agent's prompt
• •Fixed a deny or ask rule missing a command or path whose name came from a variable set as a prefix on declare, typeset, export or readonly
• •Fixed Read deny rules not applying to image paths pasted or dragged into the prompt, or to file names listed for an @-mentioned folder
• •Fixed a case where a user-installed mod could make an organization's guard skip its check; such a mod is now unloaded
• •Fixed plugin hooks stalling each redraw when a mod draws a long multi-line text holding non-Latin characters
• •Fixed repeated Ctrl+X in the agents view deleting the whole next section after the bottom session of a section was deleted
• •Fixed You should know writing its notes in English regardless of the language setting
• •Fixed a freeze after sending some very long messages
• •Fixed a slowdown when expanding the transcript (ctrl+o) or resizing over large tool output that contains non-ASCII characters such as arrows, dashes or box-drawing
• •Fixed claude respawn re-sending an earlier message to a backgrounded session that has no saved transcript instead of starting it with an empty conversation
• •Fixed Esc after an n: or Ctrl+F search in the agents view moving focus to a section header, where Ctrl+X twice would delete every session in the section
• •Fixed claude agents saving a slash command it could not deliver to a stopped session and then running it by itself the next time that session restarted
• •Fixed /ultrareview uploading uncommitted changes unfiltered for files under a git filter driver named unset or unspecified; the upload now stops and asks you to rename the driver
• •Fixed auto mode denials suggesting a permission rule that would skip the classifier for a whole tool or that Claude Code would ignore
• •Fixed claude --teleport and /teleport deleting the files in a folder that had replaced a tracked file of the same name when you chose to stash: the stash is now refused, and says why
• •Fixed Esc confirming agent view's "Press enter again to restart this session fresh" prompt
• •Fixed agent view's /loop run count freezing and its countdown disappearing after /clear; the count now restarts with the new conversation
• •Fixed --channels permission relay: a reply ID that repeats within a session is now ignored instead of approving a different prompt
• •Fixed /chrome "Reconnect extension" not restoring browser tools after a failed Chrome connection, and added an explanation when it can't (anthropics/claude-code#98135)
• •Fixed mods staying off for people who reach Claude through a gateway (ANTHROPIC_BASE_URL with ANTHROPIC_AUTH_TOKEN) and have no Anthropic account
• •Fixed replies sent from claude agents just after a background session crashed being refused after 2 seconds: they are now retried for up to 12 seconds while the session restarts
• •Fixed slash commands and answers to a multiple-choice question that claude agents could not deliver to a running session being saved and sent by themselves the next time it was restarted
• •Fixed sandboxed commands that pipe a heredoc into another command (cat <<EOF | python3) asking for approval on every run
• •Fixed claude agents failing with "Couldn't restart the background service" and background sessions stopping after a Homebrew upgrade (takes effect from the upgrade after this one)
• •Fixed agent view's "restart this session fresh" re-sending an earlier message from the session instead of starting with an empty conversation
• •Fixed Bash permission checks auto-approving some read-only commands (such as rg or git grep) whose arguments the shell would still expand as wildcards; these now prompt for approval
• •Fixed claude plugin test refusing to run after an upgrade because of an out-of-date saved setting
• •Fixed Bash permission checks auto-approving certain commands whose variable names zsh reads differently from bash; these now prompt for approval
• •Fixed a short form of a git clone option keeping the sandbox exemption from a git pattern such as git * in sandbox.excludedCommands; it is now treated like the long form
• •Fixed the first feature-flag request of a session ignoring a proxy or API endpoint set in a project's settings
• •Fixed /ultrareview of a local branch silently leaving uncommitted work out of the upload in a repository that keeps its branches outside .git (git 2.54+); it now refuses with an explanation
• •Fixed cloud sessions staying asleep after a container restart lost a pending /loop wakeup or scheduled task; Claude is now told and can schedule it again
• •Fixed the Claude apps gateway's retention sweep deleting a returning developer's identity row refreshed at the same moment, on PostgreSQL versions without the November 2025 fixes
• •Fixed sandboxed Monitor tool commands skipping the permission prompt under sandbox auto-allow; they now follow your permission rules
• •Fixed the Claude apps gateway failing to start when the certificate it presents to the identity provider has an empty subject
• •Fixed the Claude apps gateway exiting with a bare "Invalid URL" when store.postgres_url can't be parsed; the error now names the setting and says what the URL may hold
• •Fixed background agents failing with "Agent stalled" and Workflow tool subagents restarting from their prompt when a Mac woke from sleep

v1.0.3

5. Oktober 2026

• •Azure Foundry Chat Completions — The azure provider (renamed from azure-openai-responses) now also serves Foundry Chat Completions deployments, starting with azure/deepseek-v4-pro. See Azure OpenAI.
• •Codemode images saved to files — image() also writes each image to a temp file and names the path in the result, so later turns can copy or move generated images. See Generate images.
• •Renamed the Azure provider from azure-openai-responses to azure. Rename the provider key in auth.json (or run /login again), in models.json, and in settings.json (defaultProvider, enabledModels patterns, and modelThinkingLevels keys). Sessions that used the old provider fall back to another model when resumed, and their prompt cache is not reused. The AZURE_OPENAI_* environment variables are unchanged (#9714 by @jsanter27)
• •Added Azure Foundry Chat Completions deployments, starting with azure/deepseek-v4-pro (#9645, #9714 by @jsanter27)
• •Codemode image() now also saves each image to a temp file and names the path in the result, so later turns can copy or move generated images (#10310)
• •Output files (full text of truncated tool output, binary MCP resources, codemode images) are now readable only by the user
• •Home/End now always move the editor cursor to the line start/end; fullscreen transcript top/bottom moved to Ctrl+Home/Ctrl+End, which no longer move the editor cursor (#10314)
• •Fixed subscription logins such as Sign in with ChatGPT failing with refresh_token_invalidated after a request was cancelled during an OAuth token refresh
• •Fixed codemode failing for the rest of a session after a pnpm global update removed the running install, and added a restart hint when errors occur after pi was updated or removed on disk (#10439)
• •Fixed interactive sessions reporting a read EIO or setRawMode EIO crash (and asking to run /bug) when the terminal went away, e.g. after closing the window or resuming a suspended pi in a closed terminal

v18.6.1

4. Oktober 2026

• •Fixed native OpenAI context compaction for sessions containing many screenshots, preventing image-size estimates from incorrectly causing compaction requests to be rejected.
• •Fixed compatibility with Command Code DeepSeek and other DeepSeek-family models by preserving the reasoning context required for warm OpenAI Responses sessions and correctly handling incomplete DSML tool-call wrappers in visible output.
• •Fixed waiting for subagent follow-up messages: responses now appear as background jobs that can be waited on or canceled, and are delivered only once.
• •Improved /switch autocomplete so model and role suggestions use the same relevance ordering as the model picker, including support for @role aliases.
• •Fixed concurrent skill:// searches blocking other filesystem operations and delaying subagent artifact publication.
• •Fixed compatibility checks for browser relays from other OMP versions and added guidance for resolving stale connection-refused errors.
• •Fixed follow-up hashline edits being incorrectly rejected after earlier edits shifted anchored lines, while continuing to reject genuinely stale line references.
• •Fixed pi.exec() reporting exit code 0 when a process was terminated by a timeout or signal; terminated processes now report code -1.
• •Fixed /collab guests being unable to respond to setting-change approval and tool-issue report consent prompts.
• •Fixed follow-up hashline edits being rejected as anchored on lines "never displayed" after an earlier edit shifted those lines, when the replacement carries the anchored content; genuinely stale line numbers are still rejected (#14254 by @abilliontokens).
• •Fixed long /btw answers in Tern being clipped with no way to scroll: /btw now answers in the scrollable BTW history sheet (#14331 by @H4vC)
• •Fixed /btw answers longer than 4 KiB being cut off with […truncated] once they finished (#14331 by @H4vC)
• •In Tern, Esc puts the BTW history sheet away while an answer keeps streaming (/btw reopens it); x cancels the answer (#14331 by @H4vC)
• •Fixed concurrent searches through host-provided filesystem callbacks so they no longer starve other asynchronous filesystem operations, and ensured canceled searches release promptly.
• •Fixed the Space key in the Git diff pane so it stages or unstages the focused hunk instead of scrolling or acting on the wrong change.

v1.0.2

4. Oktober 2026

• •Sampling by thinking level — samplingParamsByThinkingLevel in models.json sets sampling parameters such as temperature and top_p for each thinking level on OpenAI-compatible APIs. See Configure sampling by thinking level.
• •Added samplingParamsByThinkingLevel to models.json for per-thinking-level sampling parameter overrides on OpenAI-compatible APIs. See Configure sampling by thinking level (#9776 by @mrexodia)

Reliable chat cancellation, Mac screenshot drops, and standalone SSH runtime

4. Oktober 2026

• •Standalone SSH runtime — remote SSH hosts can run an optional bundled Orca runtime without requiring Node, npm, or build tools installed on the remote machine, with full support for standard Windows accounts
• •Mac screenshot drops for Claude Code — drag temporary macOS screenshot thumbnails directly into local terminals or the new-workspace composer, automatically passing readable images to Claude Code
• •Annotate page element shortcut — trigger element inspection and annotation in the built-in browser using a customizable keyboard shortcut

v0.3.289

4. Oktober 2026

• •Updated to parity with Claude Code v2.1.289

v18.6.0

4. Oktober 2026

• •When a DeepSeek turn ends with raw <｜DSML｜…> tool-call text that could not be parsed into a real call, and no tool call was made, the broken markup is now removed from the message before it is saved to history. The agent then tells the model the tool call failed, shows it the correct format, and asks it again, at most twice in a row. Previously the markup stayed in history, and the agent stopped as if the model had finished (#14202 by @H4vC).
• •Fixed Antigravity chat and image requests sending an outdated client version when the model list came from cache, which could make newer models such as Claude Opus 5.5 unavailable.
• •When a DeepSeek model writes a broken DSML tool call (for example with the opening <｜DSML｜tool_calls> and <｜DSML｜invoke> tags missing), its closing tags are now kept in the streamed text instead of being dropped. This lets the agent remove exactly the broken call while keeping any text after it (#14202 by @H4vC).
• •Fixed DeepSeek V4 model IDs and the V4.1 Flash alias lacking version information in model identity and dashboards (#14194).
• •Fixed Antigravity models such as Claude Opus 5.5 and Sonnet 5.5 disappearing after omp models refresh. When the update check failed, omp reported an outdated Antigravity client version (2.8.0), so the server left the newer models out of the list. The fallback version is now 2.19.1.
• •DSML tool calls from DeepSeek models are now parsed on every host. This includes local servers (llama.cpp, LM Studio, vLLM), custom providers from models.yml, and gateways that weren't on the old list of supported hosts. Before, a complete <｜DSML｜tool_calls> envelope from these hosts showed up as plain text and the tool never ran (#14202 by @H4vC).
• •The /models Roles view shows which saved model preset is in effect, and Ctrl+←/→ (or p/P on the role rows, for macOS where Ctrl+←/→ switches Spaces) switches to the next or previous one, in Tern and text mode (#14210 by @H4vC)
• •Picking a model for a role in /models now puts the cursor on the model list, so ↑/↓ choose a model and Enter assigns it right away instead of moving through the sidebar and dropping the role selection; ← still reaches the providers (#14210 by @H4vC)
• •Sped up secret redaction on long conversations: it no longer slows down as history grows (#14213 by @H4vC)
• •Startup is faster with plugins that bundle large dependency trees: the extension loader no longer re-reads and re-checks the same files while loading them (e.g. ~280 ms → ~185 ms with the IDA MCP plugin) (#14219 by @H4vC)
• •Fixed an EPIPE: broken pipe unhandled rejection crashing the session when a debug adapter, eval kernel, IDA worker, or RPC server exits mid-write (seen on Windows) (#14196 by @andrebrait)
• •Fixed the Frustration page splitting DeepSeek V4 provider variants and the V4.1 Flash alias into separate model-version rows (#14194).
• •Fixed Alt+Up (restore queued steering), arrows and other escape-sequence keys on Windows acting as Esc (interrupting the turn) and typing [1;3A into the editor when the console host relays them one byte at a time (#14216 by @H4vC).
• •fix(catalog): agy anthropic models display by @H4vC in https://github.com/can1357/oh-my-pi/pull/14197
• •fix(stats): merged DeepSeek V4 frustration rows by revision by @roboomp in https://github.com/can1357/oh-my-pi/pull/14199

v1.0.1

3. Oktober 2026

• •Nix flake — nix run github:earendil-works/pi/stable runs the latest release, and nix profile add github:earendil-works/pi/stable installs it. See Install pi.
• •Project overrides for MCP servers — .pi/mcp.json and /mcp can enable, disable, or change the exposure of a user-level server for one project. See Configure servers.
• •MCP Client ID Metadata Documents — oauth.clientRegistration: "cimd" lets authorization servers allow pi by its document URL instead of dynamic registration. See Authenticate with OAuth.
• •Tool renderers for any tool — pi.registerToolRenderer() draws calls to tools that are not registered yet, such as MCP tools in resumed sessions. See Tool rendering.
• •Cloudflare Clef classifiers — @cf/cloudflare/clef and @cf/cloudflare/clef-flash are usable from codemode scripts and extensions. See Use classifier models.
• •Added a copy key (app.message.copy, default ctrl+x) to OAuth sign-in screens in /login, /mcp, and /mcp login, which copies the sign-in URL when the browser cannot be opened or the wrapped link cannot be selected.
• •Added oauth.clientRegistration: "cimd" for MCP servers, which identifies pi with its Client ID Metadata Document on pi.dev instead of dynamic client registration, so authorization servers can allow pi by URL (#10302)
• •Added project overrides for user-level MCP servers: a .pi/mcp.json entry without command or url sets only enabled, exposure, and toolExposure of the user-level server, and /mcp can enable or disable a server for the current project (#10277)
• •Added Cloudflare's Clef and Clef Flash classifier models to cloudflare-workers-ai, usable from codemode scripts and extensions (#10316 by @ndisidore, #10322 by @RealAlexandreAI)
• •Added pi.registerToolRenderer(), which chooses how calls to a tool are drawn, including tools that are not registered (#10285)
• •Added a Nix flake for macOS and Linux: nix run github:earendil-works/pi/stable runs the latest release, and nix profile add github:earendil-works/pi/stable installs it. See Install pi (#9137)
• •pi update on global npm installations now recommends migrating to the managed installation from the pi.dev installer, which pins all dependencies.
• •Anthropic tools added or redefined mid-conversation are now defined inline in the conversation, so redefining a tool under the same name keeps the prompt cache instead of resending the full tool list.
• •Fixed installations resolving vulnerable brace-expansion 5.0.9 by pinning brace-expansion 5.0.12 as a direct dependency (GHSA-q2hr-2g5m-vwhr, GHSA-qhr7-859c-m2p7, GHSA-6j4f-fj2g-mc7p) (#10288)
• •Fixed a trailing comma in --models adding an extra model to the model cycle (#10334)

v18.5.1

3. Oktober 2026

• •Added provider-reported usage cost, the unnormalized provider ID, and the requested model ID to CostEstimatorContext, allowing cost estimators to use the cost already recorded for a request instead of recomputing it from token counts.
• •Improved tool-result supersession so path reads with selectors are tracked independently from bare-path reads, while failed results supersede only earlier failed results for the same key.
• •Fixed parallel tool calls with reused or empty IDs executing with another call’s arguments or merging results; each call now executes and reports its own payload.
• •Fixed completed tool calls being retried after a transient provider-stream read error; incomplete calls from the affected turn are now discarded.
• •Fixed previously read code being removed from context when a subsequent read returned a summary, truncated content, or an error.
• •Fixed intent tracing for tools that define i as a real argument, preserving the argument and its declared schema order.
• •Fixed DeepSeek and OpenAI Responses requests failing or entering retry loops when replayed tool calls contained repaired arguments, orphaned tool results, or missing reasoning context.
• •Fixed requests to models that do not support sampling parameters from failing with HTTP 400 errors when accessed through non-native providers. Sampling parameters are now omitted for incompatible models, including requests made by chat judging, title generation, skill descriptions, and memory extraction.
• •Fixed OpenRouter BYOK usage being reported as free; provider inference costs and applicable credits charges are now included in session and status-line cost reporting.
• •Fixed Claude background and long-running bash commands losing their requested timeout and being terminated at the default deadline.
• •Fixed cleared credential cooldowns being incorrectly restored by another concurrently running session.
• •Fixed retryable Cursor provider errors, such as “Unable to reach the model provider,” from prematurely ending a turn.
• •Fixed resumed OpenAI Responses sessions losing earlier plaintext reasoning, which could cause self-hosted Responses servers to reprocess the entire context after a restart.
• •Fixed non-retryable HTTP 4xx responses being retried when their error messages contained transient-error terms such as “server_error,” “timeout,” or “overloaded.”
• •Fixed Cursor models receiving earlier multi-step tool calls as if they occurred simultaneously instead of in their original execution order.

OpenClaw2026.9.8Neu

openclaw 2026.9.8

3. Oktober 2026

• •Release notes — formatted for people, with expandable sections.
• •Changelog — plain Markdown for AI agents and tools.
• •npm package: https://www.npmjs.com/package/openclaw/v/2026.9.8
• •registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.9.8.tgz
• •integrity: sha512-G+JkNUhtpDE3cXR4AEi2NyyG9fqI/T2WUSl8ZnR8AATH8Dh1kC3qYFL7wwPoZtgHiP/cszA86PEiE0PDysxb9Q==
• •release SHA: fc23bc864e4553c2d215e479eeec47b67a0bf943
• •full release CI report: https://github.com/openclaw/releases/blob/main/evidence/2026.9.8/release-evidence.md
• •release publish: https://github.com/openclaw/openclaw/actions/runs/37089852299
• •npm preflight: https://github.com/openclaw/openclaw/actions/runs/37046778498
• •full release validation: https://github.com/openclaw/openclaw/actions/runs/37045896743
• •plugin npm publish: https://github.com/openclaw/openclaw/actions/runs/37090141905
• •plugin ClawHub submission: https://github.com/openclaw/openclaw/actions/runs/37090144556; public artifact verification follows successful release-parent completion
• •plugin ClawHub bootstrap: not needed
• •OpenClaw npm publish: https://github.com/openclaw/openclaw/actions/runs/37087759921/attempts/1
• •Telegram integration checks: waived by the release owner for 2026.9.8 (source QA, Package Acceptance, published-package E2E); not run.

Droid (Factory AI)v0.233.0Neu

CLI v0.233.0, Desktop v0.190.0: Resume with a message, Script output trimming, plus model window, custom model, and app fixes

3. Oktober 2026

• •New features: Message when resuming a session - Text after a session id in a resume command now runs in that session
• •Improvements: Script output trimming - Script results too long to keep in full now preserve their start and end
• •Bug fixes: Cut-off replies now retry - A reply that ends early on some models now retries instead of showing cut-off output
• •Bug fixes: Connector list actions - Actions in the connectors list no longer overlap a connector's category tag
• •Bug fixes: Requests over the model window - Droid now shrinks an oversized request before sending it and stops retries that cannot shrink
• •Bug fixes: Custom model error guidance - A broken custom model entry now explains the failure and leaves your other models working
• •Bug fixes: Callout spacing in messages - Callouts in a Droid message keep their padding instead of sitting against the edge
• •Bug fixes: Resuming a paused computer - A Droid Computer resuming after a pause no longer reports a failed sign-in
• •Bug fixes: Malformed tool arguments - A tool call with unreadable arguments now returns a correctable error instead of running with invented values
• •Bug fixes: Oversized message handling - A message larger than the model window is now refused with its size instead of silently trimmed
• •Bug fixes: Session history after reload - Reloading a session keeps its earliest messages above the newest page

v0.3.288

2. Oktober 2026

• •Updated to parity with Claude Code v2.1.288

v0.23.1

2. Oktober 2026

• •restore release tests and refresh required readiness check (#5278) (730deb4)
• •Review mode: final candidate
• •Intended release: patch, 0.23.1
• •Minimum required release type: patch
• •Versioning verdict: compatible
• •28 files changed (+622/-42): release automation, test fixtures, integration/example tooling, and release metadata.
• •The clean candidate contains current main a575a6e637feb9aea1b591237b007dd4991ddfba plus only six release-owned metadata files. Package, lockfile, manifest, source version and API baseline agree on 0.23.1. Snapshot source b31b9f8d13d49142a64f8873f2cc2ee40441a795 is an ancestor of the candidate.
• •Relative to v0.23.0, SDK runtime source changes only its version string. API snapshot content, dependencies, Python support and persisted schemas are unchanged.
• •First PyPI publication of the 0.23 series includes earlier migration requirements
• •Risk: 🟢 LOW with the previously reviewed migration paths. Users upgrading from 0.22.3 receive the 0.23.0 behavior changes as well as this patch.
• •Evidence: PyPI has neither 0.23.0 nor 0.23.1. The 0.23.0 release assessment in #5226 covers strict tools, approval restoration, encrypted history, resource limits, voice defaults and provider changes; this candidate does not alter those runtime paths.
• •Files: CHANGELOG.md, src/agents/version.py; unchanged 0.23.0 runtime contracts assessed in #5226.
• •Action: Carry forward the 0.23.0 migration guidance in the 0.23.1 announcement, particularly explicit strict-tool parameters, fresh legacy approvals, trusted encrypted-history import, resource-limit overrides and the explicit prior voice-model override.
• •Release checks recover without changing package behavior
• •Risk: 🟢 LOW. Test-loop initialization and required-check ownership are corrected while publication authorization remains intact.

OpenClaw2026.8.35Neu

openclaw 2026.8.35

2. Oktober 2026

• •GPT-6.1 Sol support: add the current Sol model across OpenAI routing, discovery, reasoning, harness, and Reef guard-model boundaries. (#161400, #162955)
• •Safer updates and recovery: preserve plugin settings, prevent duplicate Gateways, handle pnpm package updates without terminal failures, and retain plugin inventory through migration. (#160344, #160193, #161920, #161485) Thanks @EndeavorPioneer, @grtninja, @alkor2000, @xilopaint, and @aniruddhaadak80.
• •Reliable agent completion: preserve complete delegated and CLI answers, release suspended child capacity, recover full cron output, and prevent failed requests from consuming steered questions. (#162843, #162368, #160520, #162439) Thanks @zyz619963502zyz, @holgergruenhagen, @armstrongsam25, @davidcittadini, @jayzhou2309, and @obviyus.
• •Security and ownership hardening: keep secret-store kinds stable during rotation, restore admitted secret-egress execution, and retain explicit cron tool allowlists while repairing stale automatic snapshots. (#160926, #160760, #162432) Thanks @zachisfine, @yetval, @VACInc, and @obviyus.
• •Channel and integration reliability: repair Gmail and IMAP watchers, Matrix direct mappings, Telegram progress, remote MCP startup, and managed llama.cpp startup on clean Windows hosts. (#161503, #160413, #161727, #161546, #162376, #163093) Thanks @obviyus, @kazuyuki-eguchi, @Ayushdevo, @addyCooks, @VACInc, @Patrick-Erichsen, and @RomneyDa.
• •Performance and UI continuity: bound model-catalog waits, reduce Codex fleet heap pressure, and keep saved WebChat replies visible across history refresh races. (#161132, #162912, #162763) Thanks @jayzhou2309, @Flakedict, @obviyus, @609NFT, and @VACInc.
• •Extended-stable release preparation: align OpenClaw and every publishable official plugin to 2026.8.35 while preserving the 2026.8.34 publication contract.
• •Model compatibility: add GPT-6.1 Sol to the branch-native OpenAI and Reef compatibility owners. (#161400, #162955)
• •Update safety: preserve incompatible-plugin settings through recovery, keep retained plugin records during migration, avoid pnpm terminal failures, and carry the existing Gateway lock through container/direct startup. (#160344, #161485, #161920, #160193) Thanks @EndeavorPioneer, @aniruddhaadak80, @alkor2000, @xilopaint, and @grtninja.
• •Agent delivery: recover uncapped cron replies, preserve complete CLI subagent answers, honor skipped announcements, retain detached transcripts, release suspended child slots, and keep failed requests from replacing earlier questions with a steer. (#160520, #162843, #161542, #161091, #162368, #162439) Thanks @jayzhou2309, @zyz619963502zyz, @holgergruenhagen, @armstrongsam25, @davidcittadini, and @obviyus.
• •Cron and tools: bound thinking-catalog hydration, repair stale automatic tool snapshots without widening explicit allowlists, and deliver manual runs after their creating turn ends. (#161132, #162432, #162780) Thanks @jayzhou2309, @Flakedict, and @obviyus.
• •Sessions and tool results: reject malformed session targets, preserve spawned working directories, project deeply nested MCP results safely, and keep remote MCP bundles working in native sessions. (#161533, #162308, #160825, #162376) Thanks @wangmiao0668000666, @Takhoffman, @hpyhandsome, and @Patrick-Erichsen.
• •Channels: recover Gmail transient binds, bound IMAP backlog processing, restore Matrix direct mappings, and restore Telegram progress when hooks suppress previews. (#161503, #160413, #161727, #161546) Thanks @obviyus, @kazuyuki-eguchi, @Ayushdevo, @addyCooks, and @VACInc.
• •Runtime reliability: prevent redaction stalls, cancel stale thinking-catalog waits, pass the responding agent to TTS model selection, stop durable worker retries from freezing hosts, reduce Codex fleet heap use, and install the required Visual C++ runtime after a managed llama.cpp launch failure. (#161089, #161319, #161454, #160812, #162912, #163093) Thanks @Baumus, @drakeo338, @aounakram, @RileyJJY, @aniruddhaadak80, @obviyus, @609NFT, and @RomneyDa.
• •Secrets and sandboxing: retain secret entry kinds during value rotation and repair read-only copied skills without escaping their confined roots. (#160926, #162304, #162295) Thanks @zachisfine and @yetval.

v0.23.0

2. Oktober 2026

• •mcp: add configurable MCP listing page limits (#5133) (9a21ab1)
• •sandbox: add opt-in Docker removal protection (#5116) (ae5803f)
• •sandbox: allow configuring memory consolidation turns (#5135) (daa1bcb)
• •sessions: add an opt-in encrypted history scan budget (#5118) (a2fdb94)
• •avoid awaiting cleanup during coroutine closure (#5163) (719c4e7)
• •ci: update and group CodeQL actions together (#5262) (f76153c)
• •ci: validate release source before building distributions (#5220) (2747c1c)
• •core/extensions: respect sensitive trace capture for model metadata (#5129) (88b722d)
• •core: bound agent tool streaming callback backlogs (#5106) (f23da76)
• •core: isolate nested agent tool state across fresh runs (#5123) (46cc8d8)
• •core: preserve closed parent constraints in singleton allOf (#5131) (f010d18)
• •core: preserve guarded final outputs in agent tools (#5115) (f3a15f6)
• •core: preserve structured guardrail diagnostics and agent output during persistence (#5016) (51bcea7)
• •core: preserve tool identity during asynchronous enablement (#5136) (f2ae64c)
• •core: redact default tool failure details (#5112) (40956e0)

OpenClaw2026.8.34Neu

openclaw 2026.8.34

2. Oktober 2026

• •Extended-stable correctness rollup: backport 113 audit-selected fix units across upgrades, Doctor, authentication, sessions, channels, plugins, sandboxing, filesystem safety, model runtimes, and release packaging.
• •Complete rescan: re-evaluate the full 2026.8.33 discovery range, large mixed-purpose pull requests, and the 2026.7.35 lineage instead of advancing only from the previous backport cursor.
• •Upgrade and recovery hardening: preserve credentials, agent state, plugin inventory, transcripts, schedules, service ownership, and runtime links through upgrades, restarts, and Doctor repair.
• •Boundary fixes: tighten remote filesystem mutation, plugin and skill scanning, browser authentication, channel reply identity, private skill ingress, and scoped runtime ownership.
• •Extended-stable release preparation: align OpenClaw, publishable plugins, native version metadata, generated channel catalogs, and npm package inventories to 2026.8.34.
• •Plugins: Recover orphan installs without weakening ownership.
• •Doctor: Repair keyed multi-agent rosters without ownership (#134706)
• •Prevent device pairing migration crash on contaminated records.
• •Doctor: Preserve per-agent memory search during upgrades.
• •Doctor: Detect shared auth migration by provenance (#134808)
• •Cron: Refuse stale doctor store rewrites.
• •Gateway: Refresh model catalog after auth changes (#134361)
• •Openai: Repair stale doctor route pins.
• •Auth: Verify shared credential migration receipts (#134952)
• •Cron: Keep model aliases scoped to the selected owner (#135069)

Droid (Factory AI)v0.232.0Neu

CLI v0.232.0, Desktop v0.189.0: Legacy model warnings, session sidebar sorting, faster MCP connections, plus Windows and Slack fixes

2. Oktober 2026

• •Improvements: Model discount labels - Model pickers now state a discounted model's savings as a plain percentage off
• •Improvements: Session sidebar sorting - Sort sessions by status so ones needing input come first, and let recently active groups rise (app)
• •Improvements: Legacy model warning - Picking an older model now warns you first and offers to switch to its newer version
• •Improvements: Faster MCP connections - MCP servers you reach over HTTP now connect faster when a session starts
• •Bug fixes: Windows command output - Commands Droid runs on Windows no longer write stray output into the terminal interface
• •Bug fixes: Rejected credential errors - A turn that stops because your model credentials were rejected now reports a credential failure
• •Bug fixes: Managed settings by region - Droid now reads organization-managed settings from your organization's own region
• •Bug fixes: Plugin marketplace removal - A plugin marketplace your organization or project provides can no longer be removed by hand
• •Bug fixes: Slack channel failures - Droid now tells you when a Slack channel you asked for could not be created
• •Bug fixes: Session transcript recovery - A session whose saved history holds an unusual line separator character now loads instead of failing

Sparse checkout explorer, unencrypted secret warnings, and native Windows CLI

2. Oktober 2026

• •Sparse checkout explorer navigation — the file explorer scopes directly to configured sparse checkout directories with compact breadcrumb navigation and an inline Back button, plus an interactive preset editor to browse repository folders or add custom paths as chips
• •Unencrypted credential warnings — Settings displays a warning banner when an API key or integration token is stored in plaintext on disk without keyring encryption, making secret exposure clear on headless and minimal environments
• •Native standalone Windows CLI — replaces the Windows orca launcher with a native binary statically linked to the C runtime, running cleanly without the Visual C++ Redistributable or false-positive antivirus warnings

Codex CLIv0.160.0Neu

0.160.0

1. Oktober 2026

• •Browse older tasks in the agent command center with a keyboard-accessible “Show more” action. (#49106)
• •Select transcript text and paste with middle-click in fullscreen mode on supported local Linux X11 terminals. (#49112)
• •Start sessions outside a project with workspace defaults when policy permits, and restore saved permissions when resuming. (#49160)
• •Added opt-in Guardian review capabilities to retrieve earlier user instructions and include context from agent handoffs. (#49036, #49057)
• •Unsent queued messages now resume after reconnection once uncertain submissions are resolved, avoiding duplicate sends. (#49105)
• •The terminal UI now preserves server provider, reasoning-summary, and verbosity settings and shows the correct sessions in resume and fork history. (#49144, #49161, #49171)
• •Fixed Windows sandbox PowerShell fallbacks and long-path permission repairs, and suppressed unwanted console windows from background helpers. (#49019, #49058, #49098, #49164, #49386)
• •Subagents now retain environments that are still starting and receive their configuration or preparation failure. (#49075)
• •Prevented SQLite stalls during connection setup and logging, and surfaced initialization errors instead of masking them as timeouts. (#49032, #49102)
• •Explicit provider model catalogs no longer include unsupported bundled models or reuse stale entries after refresh failures. (#49135)
• •Clarified how provider credentials use the configured storage backend and how env_key identifies the API-key environment variable. (#49118)
• •Reduced repeated plugin-loading work by caching parsed manifests and reusing HTTP connections for remote plugin requests. (#49099, #49100)
• •Added background reclamation of unused log database space to reduce disk usage. (#49069)

v0.3.287

1. Oktober 2026

• •Added optional remote-session latency fields (first_text_post_queue_wait_ms, first_text_post_queued_behind) to the success result message
• •Fixed includePartialMessages streams sending a cut-short reply's message_stop late or never, so apps could show the reply as still in progress
• •Fixed the error for a revoked claude.ai login, which now reads "Failed to authenticate: OAuth token revoked" instead of a generic or "does not have access" message
• •Fixed a tool call to an in-process MCP server being left waiting after toggleMcpServer() disabled the server or setMcpServers() removed it
• •Fixed commands_changed arriving before init, or twice, at session start: the initialize response now includes commands registered at startup
• •Changed tool_use_result for a WebFetch or WebSearch call that steps aside for a priority "now" message to { detachedToolCall: true }; the result follows in a later turn
• •Changed tool_use_result for MCP tools: structuredContent over 1,048,576 JSON characters is left off and structuredContentOmitted: true set, except for SDK-server and MCP Apps tools
• •Updated to parity with Claude Code v2.1.287

Droid (Factory AI)v0.231.0Neu

CLI v0.231.0, Desktop v0.188.0: Transcript history paging, legacy models toggle, side chat shortcuts, template refresh, plus terminal and app fixes

1. Oktober 2026

• •Improvements: Side chat keyboard shortcuts - Side chat now takes multi-line messages and keeps its keys from acting on the main session (app)
• •Improvements: Compression progress spinner - A spinner now shows while a session's history compresses (app)
• •Improvements: Scheduled template refresh - Droid Computer templates now refresh on their own once they fall out of date
• •Improvements: Legacy models toggle - The model picker now groups older models under a legacy toggle and marks them clearly
• •Improvements: Faster first response - Droid now starts answering your first message sooner because setup work no longer blocks it
• •Improvements: Transcript history paging - Alt or Option with the arrow keys now pages a session's full saved history in the terminal
• •Bug fixes: Session settings at launch - Launching a session on a Droid Computer now keeps the model and settings you chose (app)
• •Bug fixes: Readable model errors - A model that cannot be served now reports it is temporarily unavailable instead of an empty error
• •Bug fixes: Workflow task identifiers - Droid Shield no longer flags a workflow task identifier in a commit as a secret
• •Bug fixes: Service account session privacy - Sessions you do not operate on a service account's computer stay out of your list and open read-only
• •Bug fixes: Starting local sessions - You can now start a local session without waiting for the template list to load (app)
• •Bug fixes: Questions written as text - A question Droid writes as raw markup now appears as a question you can answer
• •Bug fixes: Interrupted reply handling - A reply cut off mid-stream is now discarded instead of running unfinished tool calls
• •Bug fixes: Resumed session failures - A resumed session no longer fails when earlier reasoning cannot be reused
• •Bug fixes: Self-hosted host errors - Setting up a self-hosted GitHub or GitLab host now shows why its hostname failed to resolve

Codex CLIv0.159.3Neu

0.159.3

1. Oktober 2026

• •Eligible local sessions signed in with ChatGPT can now show optional reminders to complete account security setup. (#49744)

OpenCodev1.18.34Neu

v1.18.34

1. Oktober 2026

• •Send namespaced session and parent-session identity headers with model requests.
• •Re-sign locally compiled macOS binaries so they run reliably on macOS 27+. (@ryangamerdev)
• •Sign macOS CLI release binaries with a Developer ID.
• •docs(web): correct GPT 6.1 Sol cache pricing (#52176)
• •@metal-huang:
• •fix(tui): use path.sep for plugin name extraction in /status dialog (#52328)
• •@ryangamerdev:
• •fix(opencode): ad-hoc re-sign darwin binaries after local compile (#52183)

v0.3.286

30. September 2026

• •Added the initialize response field sdk_mcp_manifests_parked and the system/init capabilities sdk_mcp_manifests and sdk_mcp_tools_list_changed
• •Fixed foreground subagents sometimes not receiving the task-tracking tools listed in tools or allowedTools
• •Fixed an SDK MCP server listing no tools when one tool's schema cannot be converted to JSON Schema; that tool is now left out with a warning naming it
• •Fixed toggleMcpServer() not disconnecting, and failing to re-enable, an in-process MCP server created with createSdkMcpServer(), except one named claude-in-chrome
• •Changed a person's priority now message to move running shell commands, agents and MCP calls to the background and join the running turn instead of stopping it
• •Changed the TypeScript Agent SDK to leave an omitted permissionMode to Claude Code, so a settings defaultMode now applies and, on third-party providers or with telemetry off, the session starts in auto mode like claude -p; pass permissionMode: 'default' for manual approvals
• •Updated to parity with Claude Code v2.1.286

Cline 4.1.22

30. September 2026

• •New providers: Bee (by HEOSSI) and Pareto Inference (PARETO_API_KEY).
• •Direct Anthropic requests now use Anthropic's server-side refusal fallback. On OpenRouter and Cline, Anthropic models can fail over to another upstream provider instead of failing the request.
• •When a response is blocked by a content filter, Cline now says so and suggests rephrasing, instead of "Model returned empty response".
• •Refreshed the model catalog. GPT-6.1 Sol becomes the default model for OpenAI, OpenRouter, GitHub Copilot, Cortecs, Eden AI, Kilo Gateway, both LLM Gateway providers, NanoGPT, OpenCode Zen, and Requesty. Vercel AI Gateway moves to Ling 3.1 Flash, Tempr Gateway to MiMo V2.6 Flash, CrossModel and Ofox to Claude Sonnet 5.5, Pioneer to GLiNER 2.5 Decide, and Scaleway to Qwen 3.8 27B. The Cline recommended list adds Claude Sonnet 5.5 and Claude Opus 5.5. If you use one of those providers without pinning a model, expect a different default.
• •After an API error you can type and send a new message instead of only using Retry. A /compact (or /smol, /newtask) typed during recovery stays in the composer instead of being sent to the model as text.
• •If a new task fails Cline sign-in, signing in and submitting a revised prompt now starts the task with that prompt. Before, nothing happened.
• •Reset Code is now disabled when a message has no checkpoint, and no longer stays disabled for a message whose checkpoint exists (seen on slow disks). Changing the Checkpoints setting now applies to the active task, and follow-up messages typed while it applies are kept in order.
• •Canceling right after sending a message now stops the task. A cancel that landed while the turn was still being set up was ignored, and the task kept running.
• •Reasoning tokens are no longer counted twice in token usage. Cost is unchanged.
• •Amazon Bedrock: GPT-6 and GPT-5.6 route through inference profiles, and India regions (ap-south-1, ap-south-2) resolve the in. profile. OpenAI models behind inference profiles get the reasoning effort setting they support. Nova 2 Lite with high reasoning, application inference-profile ARNs, and Nova Micro no longer get requests Bedrock rejects. A legacy AWS profile setting saved without the "use profile" flag now carries over as profile authentication instead of being dropped.
• •Gateway models on providers that mix endpoints keep their own API protocol instead of falling back to the provider-wide default.

Droid (Factory AI)v0.230.0

CLI v0.230.0, Desktop v0.187.0: Attached images kept across turns, faster Windows startup, plus session, Slack, and API fixes

30. September 2026

• •Improvements: Session artifact actions - Session records now report viewed, updated, closed, and merged pull requests and issues, not only created ones
• •Improvements: Enterprise command lists - Custom blocked commands collapse behind a count, and long command lists scroll in place
• •Improvements: Faster Windows startup - Droid starts faster on Windows by skipping a redundant console setup step
• •Bug fixes: Startup with many sessions - Droid no longer freezes at startup on machines that hold thousands of sessions
• •Bug fixes: Pending questions across restarts - A question Droid is waiting on now survives a restart, so you can still answer it
• •Bug fixes: Session message order - A session now lists its messages in the order they happened
• •Bug fixes: Task reports after hooks - A background task now reports its full result even when a hook ran during the turn
• •Bug fixes: Faster reply after connection failure - Droid now starts its reply immediately instead of waiting out a retry delay after a failed connection
• •Bug fixes: Parallel tool results with images - A turn where parallel tools return images or documents no longer fails with some models
• •Bug fixes: Slack channel lists - Slack channel lists now show only real channels, not the conversations behind Droid sessions
• •Bug fixes: Images attached in earlier turns - Sending a message no longer deletes the images you attached in earlier turns
• •Bug fixes: File path chip size - A file path in a Droid message now matches the height of nearby inline code
• •Bug fixes: Image input for GLM-5.3-Flash - An image you attach now reaches the model instead of being dropped

Isolated Codex terminals, DeepSeek and Qoder harnesses, and SSH multi-factor authentication

30. September 2026

• •Isolated Codex terminals and server toggle — each Codex terminal tab runs on its own background server by default so closing or stopping one session never affects others, with a new toggle in Settings → Agents to switch back to Codex's shared server if preferred
• •DeepSeek, Qoder, Freebuff, and CodeBuddy harnesses — launch DeepSeek Harness (dsh), Qoder CLI, Freebuff, and CodeBuddy as first-class agents with live sidebar status tracking, plus ZCode session history in AI Vault and quota tracking in Usage
• •SSH keyboard-interactive MFA — connect to remote SSH hosts requiring multi-factor authentication, one-time passwords, or interactive verification prompts

Codex CLIv0.159.2

0.159.2

30. September 2026

• •Suppressed console windows flashing on Windows when Codex launches background processes and sandboxed commands. (#49385)

Gemini CLIv0.62.0

Release v0.62.0

29. September 2026

• •fix(a2a-server): add early return on unsupported store in tasks metadata endpoint by @jesussamuel-byte in https://github.com/google-gemini/gemini-cli/pull/29334
• •Changelog for v0.61.0-preview.0 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/29344
• •Changelog for v0.60.0 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/29345
• •fix(core,acp): format MCP tool call titles as structured signatures and segregate explanations by @jvargassanchez-dot in https://github.com/google-gemini/gemini-cli/pull/29341
• •chore(release): bump version to 0.62.0-nightly.20260915.gae28844fb by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/29346
• •fix(core): retain oauth refresh token on refresh and make credential deletion idempotent by @villahernandez-coder in https://github.com/google-gemini/gemini-cli/pull/29339
• •fix(ui): guard against negative layout dimensions in border rendering by @diegogodinezr in https://github.com/google-gemini/gemini-cli/pull/29347
• •test(integration): deflake run_shell_command and file-system-interactive tests by @DavidAPierce in https://github.com/google-gemini/gemini-cli/pull/29185
• •fix(core): improve PTY file descriptor cleanup and execution lifecycle management by @jesussamuel-byte in https://github.com/google-gemini/gemini-cli/pull/29340
• •chore/release: bump version to 0.62.0-nightly.20260918.g9450ade79 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/29383
• •fix(core): synchronize ConPTY process exit lifecycle and harden PTY output finalization by @jvargassanchez-dot in https://github.com/google-gemini/gemini-cli/pull/29379
• •fix(cli): suppress uncaught AbortError logs during request cancellation by @urielefrenvirtusa in https://github.com/google-gemini/gemini-cli/pull/29343
• •fix(core,cli): improve terminal buffer memory management and format Windows diagnostic paths by @jesussamuel-byte in https://github.com/google-gemini/gemini-cli/pull/29380
• •fix(vscode-ide-companion): preserve terminal focus when closing diff tabs by @amelidev in https://github.com/google-gemini/gemini-cli/pull/29378
• •fix(core): update auth error documentation link to valid anchor and add fallback (#26140) by @villahernandez-coder in https://github.com/google-gemini/gemini-cli/pull/29377

Codex CLIv0.159.1

0.159.1

29. September 2026

• •Added GPT-6.1 Sol as the default model in the bundled catalog and Amazon Bedrock Mantle and Runtime catalogs. (#49323, #49342)

v0.9.3

29. September 2026

• •Terminal shortcuts that send Escape followed by a key work again in panes. On macOS, Option+Left/Right and Option+Backspace from Ghostty's defaults or iTerm2's Natural Text Editing preset move and delete by word again, instead of typing b and f or deleting one character. Escape-based Shift+Enter bindings insert a newline in Claude Code instead of submitting. Clicking a pane still doesn't send a stray Escape. (#4751)
• •Alt+[ followed quickly by another key no longer merges into a different key. (#4751)

v0.3.285

29. September 2026

• •Added an optional read.title (the artifact's stored title) to the Artifact tool's structured read result
• •Added provider_not_allowed to startup_failure_reason and allowedProviders to the Settings type
• •Fixed sessions with CLAUDE_CODE_FORK_SUBAGENT=1: a subagent's own Agent call now runs in the foreground, so the subagent gets the child's result
• •Fixed getSessionMessages() leaving out a message sent while Claude was working when the process stopped before the reply, or when another prompt followed it with no reply in between
• •Fixed toggleMcpServer(name, false) leaving the connection open for a server that had not yet connected when the session started, or whose config was edited after it connected
• •Fixed rewind_conversation leaving a backgrounded MCP tool call running after the message that started it was removed
• •Changed Bash/PowerShell timeout to bound a run_in_background command (was ignored; default 30 min, max 2 h); the stopped task notification for a stop at that limit says why
• •Changed getSubagentMessages() to also return the messages a subagent read while it ran, such as a message sent to it; offset and limit count these rows
• •Updated to parity with Claude Code v2.1.285

v0.9.2

29. September 2026

• •The Herdr-specific pane graphics API is gone. pane.graphics.info, set, clear, and stream now return unknown_method. Apps show images by writing standard Kitty graphics to their terminal, which Herdr renders natively. (#4561)
• •Agents can report their own resume command. Herdr then reopens their exact session after a server restart, with no built-in integration needed. Self-reported agents are also cleared once their pane is back at an idle shell. The new Add Herdr support to your agent guide covers state, resume, and release for agent authors. (#4687)
• •Use more than one prefix key: prefix = ["ctrl+space", "ctrl+s"]. Every entry enters the same prefix mode, and prefix+? lists them all. (#4653, thanks @JJLiebig)
• •Go To shows every agent and terminal as its own row, grouped by workspace, with its status and path. Left and Right jump between workspaces. (#4384)
• •Bind keys.clear_pane to clear the focused pane's screen and scrollback while keeping the current prompt line. It is unbound by default and leaves full-screen apps such as Vim alone. (#4383)
• •herdr machine status checks saved machines without prompting. herdr machine reconnect finishes SSH authentication, including MFA, in your terminal. Open clients recheck failed machines every 30 seconds, so no restart is needed after fixing a connection. (#3763)
• •Interactive machine add finds the Herdr sessions already running on the host and lets you pick one. --label is optional; the machine is named after its SSH host. (#4204, #4678, thanks @JJLiebig and @dhh)
• •terminal session control accepts terminal.mouse events, so bridge clients can click buttons in apps that enable mouse reporting. (#4685)
• •Restored agents start one at a time, 100 ms apart by default, instead of all at once. Change the spacing with [session] startup_per_agent_delay_ms. (#4102, thanks @JJLiebig)
• •Images render faster and more reliably. Local Ghostty receives image data through temporary files instead of terminal output. Popups and notifications crop images around themselves instead of hiding them. Images that scroll out of view stay loaded, so scrolling back no longer resends them. (#4561, #4652, #4686)
• •SSH connections request compression. On slow links, remote panes catch up after scrolling in a fraction of the time. (#4340)
• •Scrolling output on saved machines sends only the rows that changed, cutting bandwidth for build logs and streaming agents. Older clients and servers keep working with the previous format. (#4711)
• •New panes set TERM_PROGRAM=herdr and TERM_PROGRAM_VERSION. They no longer inherit terminal session IDs, such as iTerm2's, or Claude Code session markers from the terminal that started the server. (#4104)
• •Windows panes default to PowerShell 7 (pwsh) when it is installed, falling back to Windows PowerShell. An explicit default_shell still wins. (#4297, thanks @JJLiebig)
• •Closing the last tab of a workspace now asks for confirmation. (#4379, #4409, thanks @minatoaquaMK2)

Codex CLIv0.159.0

0.159.0

29. September 2026

• •Opt-in instant_interrupt lets new input steer Codex during model responses or long-running code-mode calls. (#48135, #48141)
• •New sessions get a compact welcome screen and consistent headers, with occasional tips during and after turns. (#48513, #48562, #48352)
• •The warnings viewer dismisses reviewed warnings when closed; press k to keep one for later. (#48205, #48206)
• •You can scroll the transcript while deciding whether to implement a plan. (#48805)
• •Native Mermaid rendering supports more flowchart edges, labels, and node groups. (#48814, #48895)
• •App-server clients can paginate thread history from a specific item. (#48151)
• •Windows launches avoid stray console windows for MCP servers, code-mode hosts, and piped commands; restrictive launchers can fall back to embedded mode. (#48138, #48238, #48483, #48491)
• •Copying transcript selections preserves Markdown tables, formatting, and significant whitespace. More terminals now copy automatically on selection. (#48548, #48549, #48469)
• •Blank sessions retain drafts when switching tasks, and threads can be archived and listed before their first turn. (#48628, #48828, #48199)
• •Local ChatGPT sign-in opens the browser reliably; onboarding also provides a shortcut to copy the login link. (#48502, #48544)
• •Approved commands retain explicit filesystem denials, and .aws directories are protected by default under writable roots. (#48155, #48176)
• •Fixed macOS TLS access in network-enabled sandboxes and remote environments that require proxy access. (#48565, #48198)
• •Removed automatic follow-up prompt suggestions and the tui.prompt_suggestions setting. (#48621)
• •Removed the bundled plugin-creator skill. (#48604)

Droid (Factory AI)v0.229.0

CLI v0.229.0, Desktop v0.186.0: Custom model management, PDF viewer, quoted replies, voice dictation key, plus terminal and app fixes

29. September 2026

• •New features: Custom models in terminal - You can now add, edit, and remove your own custom models from the terminal
• •New features: Scheduled loops indicator - A pill above the chat input lists a session's loops and can pause, resume, or stop them (app)
• •New features: Quote a Droid reply - Select text in a Droid response and add it to your next message as a quote (app)
• •New features: Voice dictation key - Pick a single key that starts and stops voice dictation, or turn the shortcut off (app)
• •New features: PDF viewer - PDF files now open in a scrolling viewer with a page rail, thumbnails, and zoom (app)
• •New features: Save files outside the workspace - The Files panel can now save a file that lives outside your workspace folder (app)
• •Improvements: Custom model JSON editing - You can now edit one of your own custom models as a form or as raw JSON (app)
• •Improvements: Session list edge fades - The session list now fades at its top and bottom edges while you scroll (app)
• •Improvements: Smoother file opening - Opening a file from a tool call no longer stutters as the side pane slides in (app)
• •Improvements: Faster repository lists - Pages that list your repositories now load much faster
• •Improvements: Side chat controls - Side chat now shows its tool calls live and lets you stop or clear a question (app)
• •Improvements: Idle Slack channel archiving - Channels Droid opens for a session in Slack are archived once they sit idle
• •Improvements: Migration files pill - A Migration pill above the chat input opens the files for an active migration (app)
• •Bug fixes: Mobile onboarding payment - Onboarding on a phone now walks through plan selection and billing as separate steps
• •Bug fixes: Diagram pan and zoom - Panning an expanded diagram no longer shrinks it, and pinch and arrow keys work (app)

OpenCodev1.18.33

v1.18.33

28. September 2026

## Core ### Bugfixes - Cloudflare AI Gateway models now honor provider response and stream timeouts. (@danlapid) - MCP browser launch failures are now reported when the launcher exits immediately. - Debug configuration output now redacts credentials and sensitive headers. - Gemini thinking defaults and effort options now match the supported controls across model generations. (@markmcd) Thank you to 5 community contributors: - @dc85: - docs(web): add Claude Opus 5.5, GPT 6 Sol, and GPT 6 Luna to Zen (#50708) - @vglafirov: - maint(gitlab): bump gitlab-ai-provider to 6.16.0 (#50742) - @markmcd: - fix(gemini): switch thinking default logic (#50841) - @remorses: - docs(web): link kimaki to product website (#49735) - @danlapid: - fix(opencode): apply provider timeouts to Cloudflare AI Gateway models (#51549)